ggml_cont: fix issue with transposed tensors when one dimension is 1

[smeso]

When using multiple threads, it is not enough to check for the tensors to be contiguous for
ggml_compute_forward_dup_same_cont to work correctly.
The tensors strides also need to match.

[ggerganov]

The following should be more precise I think:

diff --git a/src/ggml.c b/src/ggml.c
index 567084f..c27581c 100644
--- a/src/ggml.c
+++ b/src/ggml.c
@@ -8113,8 +8113,7 @@ static void ggml_compute_forward_dup_same_cont(
     GGML_ASSERT(ggml_is_contiguous(dst) && ggml_is_contiguous(src0));
     GGML_ASSERT(src0->type == dst->type);
 
-    const size_t nb00 = src0->nb[0];
-    const size_t nb0 = dst->nb[0];
+    const size_t nb0 = ggml_type_size(src0->type);
 
     const int ith = params->ith; // thread index
     const int nth = params->nth; // number of threads
@@ -8128,8 +8127,8 @@ static void ggml_compute_forward_dup_same_cont(
     if (ie0 < ie1) {
         memcpy(
             ((char *)  dst->data + ie0*nb0),
-            ((char *) src0->data + ie0*nb00),
-            (ie1 - ie0) * ggml_type_size(src0->type));
+            ((char *) src0->data + ie0*nb0),
+            (ie1 - ie0) * nb0);
     }
 }
 
@@ -9072,8 +9071,7 @@ static void ggml_compute_forward_dup_bytes(
 
     GGML_TENSOR_UNARY_OP_LOCALS;
 
-    if (ggml_is_contiguous(src0) && ggml_is_contiguous(dst) &&
-        nb00 == nb0 && nb01 == nb1 && nb02 == nb2 && nb03 == nb3) {
+    if (ggml_is_contiguous(src0) && ggml_is_contiguous(dst)) {
         ggml_compute_forward_dup_same_cont(params, dst);
         return;
     }